Deep Learning-based Segmentation of Pleural Effusion From Ultrasound Using Coordinate Convolutions
This addresses the issue of intra-/inter-observer variability in manual effusion measurement in LMIC settings where experienced radiologists are scarce.
The paper tackles the problem of automating pleural effusion segmentation from ultrasound images in low-to-middle income countries, achieving median Dice Similarity Coefficients of 0.82 and 0.74 on two datasets, with an improvement to 0.85 using coordinate convolutions on one dataset.
In many low-to-middle income (LMIC) countries, ultrasound is used for assessment of pleural effusion. Typically, the extent of the effusion is manually measured by a sonographer, leading to significant intra-/inter-observer variability. In this work, we investigate the use of deep learning (DL) to automate the process of pleural effusion segmentation from ultrasound images. On two datasets acquired in a LMIC setting, we achieve median Dice Similarity Coefficients (DSCs) of 0.82 and 0.74 respectively using the nnU-net DL model. We also investigate the use of coordinate convolutions in the DL model and find that this results in a statistically significant improvement in the median DSC on the first dataset to 0.85, with no significant change on the second dataset. This work showcases, for the first time, the potential of DL in automating the process of effusion assessment from ultrasound in LMIC settings where there is often a lack of experienced radiologists to perform such tasks.